Infrared and visible remote sensing image matching is significant for the utilization of remote sensing images to obtain scene information. However, due to the large number of sparse and repetitive texture regions in multi-modal remote sensing scenes, feature extraction poses serious difficulties. To address these challenges, this letter proposes Attention-based Features (AttFeat). First, to solve the problem of coarse feature representation, we propose the Parallel Channel and Spatial Attention (PCSA) Module, which focuses on important spatial locations and provides richer cross-channel representation. Second, to address the lack of contextual information, we propose the Squeezed-Axis and Window Transformer (SAWFormer), which can obtain a dense global receptive field at a lower cost while retaining rich details. Finally, multi-modal recoupling loss is utilized to optimize the relationship between the rich feature description and large receptive field. Extensive experiments on aviation and remote sensing multi-modal datasets demonstrate the superiority of our algorithm and the effectiveness of the proposed modules. In terms of detection and matching performance, AttFeat outperforms the baseline ReDFeat by 10.81% and 15.48%, respectively. The dataset and code will be released at: AttFeat.

Object detection is a crucial but challenging task in remote sensing images. Thanks to the emergence of convolution neural networks (CNNs ), object detection has made significant progress. However, there are still two significant issues that must be addressed: 1) Since small targets are distributed at any angle, the features extracted by traditional convolution are incomplete and 2) the objects in remote sensing images are small and dense, resulting in missed detections and false detections during the detection process. In this letter, we innovatively propose to obtain more semantic information to help remote sensing detection tasks solve these two problems. To achieve this goal, we design two novel modules: an adaptive feature extraction module (AFEM) and a tridirectional feature fusion module (TRFFM) to improve detection capabilities in small target-dense scenarios. More specifically, AFEM combines local features with global features to adaptively fit the receptive field of rotating targets. TRFFM establishes multiple paths between different layers of the feature pyramid and uses a weighted special fusion mechanism to obtain higher-quality feature maps. Extensive experiments on two challenging remote datasets, optical remote sensing images (DIOR) and VisDrone2019, results reached 75.4%AP50and 33.2%APrespectively, which verified the superiority of our method in terms of accuracy and adaptability. The code has been open-sourced at https://github.com/GGD777/SIFANet.

Aerial images usually contain a large number of truncated and small objects, which poses a significant challenge for object detection. Existing methods have introduced additional learnable components in the pipeline and adopted multistage training approaches, but they have not solved the problem of achieving end-to-end detection. To address this issue, we propose a novel no-extra components density map cropping (NE-CDMNet) method to utilize the spatial and contextual information between objects to improve detection performance. Furthermore, we introduce a new query selection (QS) scheme that utilizes confidence scores to select the top-K features from the encoder, helping the model better leverage the position information for extracting more comprehensive content features. Finally, we incorporate the local-global fusion (LGF) algorithm to combine the detection results from the original image and the density-cropped image. We conducted extensive experiments on two widely used public aerial datasets. Results reveal that the proposed method achieves the best performance compared with other state-of-the-art methods, whose 35.3% AP on the VisDrone-DET2019 dataset and 79.7% mAP on object detection in optical remote sensing image (DIOR) dataset, demonstrate the effectiveness of our method.

To enhance the efficiency and accuracy of the on-orbit focusing of Earth observation satellites, this study proposes a method based on multistar imaging. Specifically, the proposed method quantitatively evaluates the defocusing state of a space optical camera and estimates the optimal position of its photosensitive surface of detector (PSD). An experimental platform is established to capture star images, and the performance of the algorithm is evaluated based on indexes such as focusing accuracy and robustness. Moreover, the algorithm is compared to the single-star-imaging-based algorithm. Consequently, the effectiveness of the proposed algorithm is validated. Next, to demonstrate the application of the algorithm to real-time on-orbit focusing, field programmable gate arrays (FPGAs) are used. Specifically, the performance of the multistar-imaging-based algorithm in practical engineering applications is verified using space camera on-orbit star imaging data, and its performance is compared with that of the single-star-imaging-based algorithm. In ground tests, the maximum focusing error of the algorithm based on multistar imaging is 0.00075 mm. During robustness tests involving variations in the focusing step, star centroid distribution uniformity, and image noise, its maximum error is 0.0021 mm. Further, when the signal-to-noise ratio (SNR) of the image exceeds 20 dB, the focusing accuracy and goodness of fit (GOF) of the algorithm based on multistar imaging are better compared to those of the single-star-imaging-based algorithm. The prototype verification results present an error of 1.623% relative to the baseline data. Using on-orbit star imaging data, the error between the optimal PSD position and the actual ideal PSD position is calculated to be 0.01528 mm. These results indicate that the auto-focusing algorithm proposed in this article demonstrates high focusing accuracy and robustness against external factors such as focusing step changes, centroid distribution uniformity variations, image noise differences, and star brightness changes. Moreover, it outperforms the single-star-imaging-based algorithm. Hardware deployment verification reveals that the computing resources and calculation accuracy of the algorithm within the XC7K325T environment satisfy operational requirements. Thus, the proposed algorithm can be employed for the on-orbit focusing tasks of space cameras, satisfying image quality requirements with enhanced focusing accuracies.

Due to the influence of atmospheric scattering, the quality of remote sensing images is degraded, which severely limits the utility of remote sensing images. In this article, a novel dehazing algorithm for a single remote sensing image is proposed based on a low-rank and sparse prior (LSP). According to an atmospheric scattering model, the dark channel of a hazy image is decomposed into two parts: the dark channel of direct attenuation with sparseness and the atmospheric veil with low rank. The prior is obtained from the overall decomposition of the image rather than the patches of the image; therefore, the image pixel changes of the local blocks have little influence on the prior. Considering different resolutions of remote sensing images, the calculations of blocks involved in this article are completed by adaptive methods. The principal component pursuit and alternating direction multiplier method (PCP-ADMM) combined with the adaptive threshold shrinkage method are used for low-rank and sparse decomposition, therefore, the coarse estimation of the atmospheric veil is obtained. The guided filter with adaptive radius is used to refine it, and then the accurate atmospheric light is estimated. Finally, using the deformed atmospheric scattering model based on the atmospheric veil and atmospheric light, the haze-free image is restored. Extensive experimental results on publicly available data sets show that the dehazed images have abundant detail, high contrast, and minimal color distortion when using the proposed method, which is competitive with most state-of-the-art technologies.